SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy

doi:10.3390/s19204457

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 精密感知与控制

	SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy
	She, Haotian 4,5; Zhu, Jinying 1,3; Tian, Ye 4,5; Wang, Yanchao 4,5; Yokoi, Hiroshi 2,3; Huang, Qiang 4,5
刊名	SENSORS
	2019-10-02
卷号	19 期号:20 页码:15
关键词	surface EMG signal feature extraction Stockwell transform hand movement recognition
DOI	10.3390/s19204457
通讯作者	Zhu, Jinying(zhujinying01@163.com) ; Tian, Ye(tianye7248@bit.edu.cn)
英文摘要	Feature extraction, as an important method for extracting useful information from surface electromyography (SEMG), can significantly improve pattern recognition accuracy. Time and frequency analysis methods have been widely used for feature extraction, but these methods analyze SEMG signals only from the time or frequency domain. Recent studies have shown that feature extraction based on time-frequency analysis methods can extract more useful information from SEMG signals. This paper proposes a novel time-frequency analysis method based on the Stockwell transform (S-transform) to improve hand movement recognition accuracy from forearm SEMG signals. First, the time-frequency analysis method, S-transform, is used for extracting a feature vector from forearm SEMG signals. Second, to reduce the amount of calculations and improve the running speed of the classifier, principal component analysis (PCA) is used for dimensionality reduction of the feature vector. Finally, an artificial neural network (ANN)-based multilayer perceptron (MLP) is used for recognizing hand movements. Experimental results show that the proposed feature extraction based on the S-transform analysis method can improve the class separability and hand movement recognition accuracy compared with wavelet transform and power spectral density methods.
资助项目	Beijing Advanced Innovation Center of Intelligent Robots and Systems[2016IRS23]
WOS关键词	EMG PATTERN-RECOGNITION ; SURFACE EMG ; PROSTHETIC HANDS ; FEATURE-PROJECTION ; CLASSIFICATION ; WAVELET ; RECORDINGS ; SIGNALS ; SCHEME ; ROBUST
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
语种	英语
出版者	MDPI
WOS记录号	WOS:000497864700105
资助机构	Beijing Advanced Innovation Center of Intelligent Robots and Systems
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/29377]
专题	精密感知与控制研究中心_精密感知与控制
通讯作者	Zhu, Jinying; Tian, Ye
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Electrocommun, Sch Informat & Engn, Tokyo 1638001, Japan 3.Beijing Adv Innovat Ctr Intelligent Robot & Syst, Beijing 100081, Peoples R China 4.Beijing Inst Technol, Sch Mechatron Engn, Beijing 100081, Peoples R China 5.Minist Educ, Key Lab Biomimet Robots & Syst, Beijing 100081, Peoples R China
推荐引用方式 GB/T 7714	She, Haotian,Zhu, Jinying,Tian, Ye,et al. SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy[J]. SENSORS,2019,19(20):15.
APA	She, Haotian,Zhu, Jinying,Tian, Ye,Wang, Yanchao,Yokoi, Hiroshi,&Huang, Qiang.(2019).SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy.SENSORS,19(20),15.
MLA	She, Haotian,et al."SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy".SENSORS 19.20(2019):15.